tags:
- pytorch
CNN Leukemia Classifier
Model Description
This Convolutional Neural Network (CNN) model is designed for the classification of leukemia images into one of four classes. It was developed for the Quito AI Day event by Sebastian Sarasti. The model leverages a series of convolutional layers followed by fully connected layers to process and classify images effectively.
Model Architecture
The model consists of the following layers:
Convolutional Layer: 3 input channels, 128 output channels, 3x3 kernel size, stride 1, padding 1
ReLU Activation
Max Pooling Layer: 2x2 kernel size
Dropout Layer: 0.3 dropout rate
Convolutional Layer: 128 input channels, 64 output channels, 3x3 kernel size, stride 1, padding 1
ReLU Activation
Max Pooling Layer: 2x2 kernel size
Dropout Layer: 0.3 dropout rate
Convolutional Layer: 64 input channels, 32 output channels, 3x3 kernel size, stride 1, padding 1
ReLU Activation
Max Pooling Layer: 2x2 kernel size
Dropout Layer: 0.3 dropout rate
Convolutional Layer: 32 input channels, 8 output channels, 3x3 kernel size, stride 1, padding 1
ReLU Activation
Max Pooling Layer: 2x2 kernel size
Dropout Layer: 0.3 dropout rate
Flatten Layer
Fully Connected Layer: 1568 input features, 512 output features
ReLU Activation
Dropout Layer: 0.5 dropout rate
Fully Connected Layer: 512 input features, 4 output features
Dataset
The model was trained on the Leukemia dataset from Kaggle, which consists of images labeled into different leukemia types.
Usage
To use this model, you can load it from the Hugging Face Hub as follows:
from transformers import AutoModel
model = AutoModel.from_pretrained("path/to/your/model")